- Number
- 9805264
- Published
- 2017-10-31
- Filed
- 2015-10-19
- Assignee
- Disney Enterprises, Inc.
- Inventors
- Kuznetsova; Alina, Hwang; Sung Ju, Sigal; Leonid
- CPC
- G06F18/2132; G06V20/41; G06V20/40; G06V10/255; G06V10/7715
- Verdict
- Low Notable software
- Source
- Google Patents · FreePatentsOnline
The keeper's note
An incrementally-expanding object detection model that learns to identify new object classes in video without full retraining.
Abstract
Techniques disclose an incrementally expanding object detection model. An object detection tool identifies, based on an object detection model, one or more objects in a sequence of video frames. The object detection model provides an object space including a plurality of object classes. Each object class includes one or more prototypes. Each object is classified as being an instance of one of the object classes. Each identified object is tracked across at least one of the frames. The object detection tool generates a measure of confidence for that object based on the tracking. Upon determining that the measure of confidence exceeds a threshold, the object detection tool adds a prototype of the instance to the object detection model.
Background
BRIEF DESCRIPTION OF THE DRAWINGS(1) So that the manner in which the above recited features of the present disclosure can be understood in detail, a more particular description of the disclosure, briefly summarized above, may be had by reference to embodiments, some of which areillustrated in the appended drawings. It is to be noted, however, that the appended drawings illustrate only exemplary embodiments and are therefore not to be considered limiting of its scope, may admit to other equally effective embodiments.(2) FIG. 1 illustrates an example computing environment, according to one embodiment.(3) FIG. 2 further illustrates the computing system described relative to FIG. 1, according to one embodiment.(4) FIG. 3 further illustrates the object detection tool described relative to FIGS. 1 and 2, according to one embodiment.(5) FIG. 4 illustrates an example of an initial object detection model, according to one embodiment.(6) FIG. 5 illustrates an example of an expanded object detection model, according to one embodiment.(7) FIG. 6 illustrates a method of incrementally expanding an object detection model, according to one embodiment.(8) To facilitate understanding, identical reference numerals have been used, where possible, to designate identical elements that are common to the figures. It is contemplated that elements and features of one embodiment may be beneficially incorporated in other embodiments without further recitation.DETAILED DESCRIPTION(9) Embodiments present
Claims
1. A method, comprising: identifying, based on an object detection model, one or more objects in a first sequence of video frames of a plurality of sequences of video frames, wherein the object detection model provides an object space including a plurality of object classes, wherein each object is classified as being an instance of one of the classes, and wherein each object class includes one or more prototypes representing an instance of an object associated with the object class; and foreach identified object: tracking the object across at least one of the frames, generatinga measure of confidence for the object based on the tracking, wherein the measure of confidence indicates a degree that the object does not correspond to any of the one or more prototypes currently associated with the object class, and upon determining that the measureof confidence exceeds a threshold, adding a prototype representative of the instance to the object detection model.
8. A non-transitory computer-readable storage medium having instructions, which, when executed on a processor, perform an operation comprising: identifying, based on an object detection model, one or more objects in a first sequence of video frames of a plurality of sequences of video frames, wherein the object detection model provides an object space including a plurality of object classes, wherein each object is classified as being an instance of one of the object classes, and wherein each object class includes one or more prototypes representing an instance of an object associated with the object class; and for each identified object: tracking the object across at least one of the frames, generating a measure of confidence for the object based on the tracking, wherein the measure of confidence indicates a degree that the object does not correspond to any of the one or more prototypes currently associated with the object class, and upon determining that the measure of confidence exceeds a threshold, adding a prototype representative ofthe instance to the object detection model.
15. A system, comprising: a processor; and a memory storing program code, which, when executed on the processor, performs an operation comprising: identifying, based on an object detection model, one or more objects in a first sequence of video frames of a plurality of sequences of video frames, wherein the objectdetection model provides an object space including a plurality of object classes, whereineach object is classified as being an instance of one of the object classes, and wherein each object class includes one or more prototypes representing an instance of an object associated with the object class, and for each identified object: tracking the object acrossat least one of the frames, generating a measure of confidence for the object based on the tracking, wherein the measure of confidence indicates a degree that the object does not correspond to any of the one or more prototypes currently associated with the object class, and upon determining that the measure of confidence exceeds a threshold, adding a prototype representative of the instance to the object detection model.